High-Performance AI-Native Web Server — built in C & Assembly for ultra-fast AI inference and streaming.

This repository features an application example for Siemens' Industrial AI Vision Blueprint

g023's TurboXInf 🚀: 2x+ faster inference for Qwen3-1.77B or Qwen3.5-2B on RTX 3060! Custom Triton INT8 GEMV kernels halve memory traffic by fusing dequantization, paired with torch.compile. Hits 113 tok/s (vs 56.4 baseline) with no quality loss with INT8 even better results for INT4. MIT License.

A comprehensive framework for multi-node, multi-GPU scalable LLM inference on HPC systems using vLLM and Ollama. Includes distributed deployment templates, benchmarking workflows, and chatbot/RAG pipelines for high-throughput, production-grade AI services